© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 11256
    Prev
    Next
    INDEX
    Explanations

    proper names related to the surname "Cox"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Cox" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theft
    -0.65
     cartel
    -0.64
     lockout
    -0.58
    keepers
    -0.58
     illeg
    -0.57
     Secrets
    -0.56
     Saving
    -0.56
    inen
    -0.55
     Rite
    -0.55
     Camera
    -0.55
    POSITIVE LOGITS
    icut
    0.89
    nown
    0.88
    peria
    0.86
    idious
    0.84
    odus
    0.81
    raltar
    0.81
    nian
    0.80
    ham
    0.80
    boro
    0.79
    TERN
    0.77
    Activations Density 0.101%

    No Known Activations